[Qemu-devel] [PATCH v6 25/28] qmp/migration: new command migrate-recover

[Peter Xu <peterx@redhat.com>]

The first allow-oob=true command.  It's used on destination side when
the postcopy migration is paused and ready for a recovery.  After
execution, a new migration channel will be established for postcopy to
continue.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 migration/migration.c | 26 ++++++++++++++++++++++++++
 migration/migration.h |  1 +
 migration/savevm.c    |  3 +++
 qapi/migration.json   | 20 ++++++++++++++++++++
 4 files changed, 50 insertions(+)

diff --git a/migration/migration.c b/migration/migration.c
index cf3a3f416c..bb57ed9ade 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1422,6 +1422,32 @@ void qmp_migrate_incoming(const char *uri, Error **errp)
     once = false;
 }
 
+void qmp_migrate_recover(const char *uri, Error **errp)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    if (mis->state != MIGRATION_STATUS_POSTCOPY_PAUSED) {
+        error_setg(errp, "Migrate recover can only be run "
+                   "when postcopy is paused.");
+        return;
+    }
+
+    if (mis->postcopy_recover_triggered) {
+        error_setg(errp, "Migrate recovery is triggered already");
+        return;
+    }
+
+    /* This will make sure we'll only allow one recover for one pause */
+    mis->postcopy_recover_triggered = true;
+
+    /*
+     * Note that this call will never start a real migration; it will
+     * only re-setup the migration stream and poke existing migration
+     * to continue using that newly established channel.
+     */
+    qemu_start_incoming_migration(uri, errp);
+}
+
 bool migration_is_blocked(Error **errp)
 {
     if (qemu_savevm_state_blocked(errp)) {
diff --git a/migration/migration.h b/migration/migration.h
index 88f5614b90..581bf4668b 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -65,6 +65,7 @@ struct MigrationIncomingState {
     QemuSemaphore colo_incoming_sem;
 
     /* notify PAUSED postcopy incoming migrations to try to continue */
+    bool postcopy_recover_triggered;
     QemuSemaphore postcopy_pause_sem_dst;
     QemuSemaphore postcopy_pause_sem_fault;
 };
diff --git a/migration/savevm.c b/migration/savevm.c
index d40092a2b6..5f41b062ba 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2182,6 +2182,9 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis)
     /* Notify the fault thread for the invalidated file handle */
     postcopy_fault_thread_notify(mis);
 
+    /* Clear the triggered bit to allow one recovery */
+    mis->postcopy_recover_triggered = false;
+
     error_report("Detected IO failure for postcopy. "
                  "Migration paused.");
 
diff --git a/qapi/migration.json b/qapi/migration.json
index 055130314d..dfbcb02d4c 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -1172,3 +1172,23 @@
 # Since: 2.9
 ##
 { 'command': 'xen-colo-do-checkpoint' }
+
+##
+# @migrate-recover:
+#
+# Provide a recovery migration stream URI.
+#
+# @uri: the URI to be used for the recovery of migration stream.
+#
+# Returns: nothing.
+#
+# Example:
+#
+# -> { "execute": "migrate-recover",
+#      "arguments": { "uri": "tcp:192.168.1.200:12345" } }
+# <- { "return": {} }
+#
+# Since: 2.12
+##
+{ 'command': 'migrate-recover', 'data': { 'uri': 'str' },
+  'allow-oob': true }
-- 
2.14.3